Abstract
The design of computer-assisted decision (CAD) systems for different biomedical imaging scenarios is a challenging task in computer vision. Sometimes, this challenge can be attributed to the image acquisition mechanisms since the lack of control on the cameras can create different visualizations of the same imaging site under different rotation, scaling, and illumination parameters, with a requirement to get a consistent diagnosis by the CAD systems. Moreover, the images acquired from different sites have specific colors, making the use of standard color spaces highly redundant. In this paper, we propose to tackle these issues by introducing novel region-based texture, and color descriptors. The proposed texture features are based on the usage of analytic Gabor filters (for compensation of illumination variations) followed by the calculation of first-and second-order statistics of the filter responses and making them invariant using some trivial mathematical operators. The proposed color features are obtained by compensating for the illumination variations in the images using homomorphic filtering followed by a bag-of-words approach to obtain the most typical colors in the images. The proposed features are used for the identification of cancer in images from two distinct imaging modalities, i.e., gastroenterology and dermoscopy. Experiments demonstrate that the proposed descriptors compares favorably to several other state-of-the-art methods, elucidating on the effectiveness of adapted features for image characterization.

Abstract
In this paper, deep convolutional neural networks are used to segment heart sounds into their main components. The proposed method is based on the adoption of a novel deep convolutional neural network architecture, which is inspired by similar approaches used for image segmentation. A further post-processing step is applied to the output of the proposed neural network, which induces the output state sequence to be consistent with the natural sequence of states within a heart sound signal (S1, systole, S2, diastole). The proposed approach is tested on heart sound signals longer than 5 seconds from the publicly available PhysioNet dataset, and it is shown to outperform current state-of-the-art segmentation methods by achieving an average sensitivity of 93.4% and an average positive predictive value of 94.5% in detecting S1 and S2 sounds.

Abstract
Automatic and simultaneous electrocardiogram (ECG) and phonocardiogram (PCG) segmentation is a good example of current challenges when designing multi-channel decision support systems for healthcare. In this paper, we implemented and tested a Montazeri coupled hidden Markov model (CHMM), where two HMM's cooperate to recreate the "true" state sequence. To evaluate its performance, we tested different settings (two fully connected and two partially connected channels) on a real dataset annotated by an expert. The fully connected model achieved 71% of positive predictability (P+) on the ECG channel and 67% of P+ on the PCG channel. The partially connected model achieved 90% of P+ on the ECG channel and 80% of P+ in the PCG channel. These results validate the potential of our approach for real world multichannel application systems.

Abstract
Classification of texture images, especially in cases where the images are subjected to arbitrary rotation and scale changes due to dynamic imaging conditions is a challenging problem in computer vision. This paper proposes a novel methodology to obtain rotation and scale invariant texture features from the images. The feature extraction for a given image involves the calculation of the averages of Gabor filter responses at various scales and orientations. For rotation and scaling of images, these averages indicate the respective shifts in the features. These shifts are normalized by doing summations of Gabor responses across scales and then taking the magnitude of Discrete Fourier Transforms across the resulting features and vice versa thus giving us scale and rotation invariant texture features. The proposed features are used for identifying cancer in the vital stained magnification endoscopy images. Experiments demonstrate the superiority of the proposed feature set over several other state-of-the-art texture feature extraction methods with around 90% classification accuracy for identifying cancer in gastroenterology images.

Abstract
Swallowing is a dynamic, complex and synergistic process, composed of three phases with a refined neuromotor control. A malfunction of this process, denominated dysphasia, can occur in any age like a result of congenital, structural, functional and/or medical problems. The quantitative analysis of this process is crucial to understand the temporal relations between the mechanisms of the oropharyngeal deglutition. Designing a software to support the qualitative and quantitative analysis of the swallowing process through dynamic images obtained by videofluoroscopy is the main motivation and objective of this work. First, a survey of requirements for such a software was made, consisting in a research protocol for assessing dysphagia by videofluoroscopy. Secondly, best practices in human-computer interaction were used to design a conceptual model for the proposed software. Two protocols were selected for the assessment of dysphagia by videofluoroscopy: the Protocol of Boston and the Protocol used in the Hospital Privado da Trofa. These protocols allowed the identification of several events that are evaluated in the swallowing process and that can be recorded, measured and quantified during ingestion of the bolus. The second phase resulted in a conceptual model for an interactive system embodying the evaluation protocol selected and contemplates the integration of automatic algorithms for qualitative and quantitative evaluation of the parameters of swallowing. The proposed software model has a high potential to be a useful tool for assessing parameters of swallowing.

Abstract
Recent advances in the area of computer vision has led to the development of various assisted diagnostics systems for the detection of melanoma in the patients. Texture and color are considered as two fundamental visual characteristics which are vital for the detection of melanoma. This paper proposes the use of a combination of texture and color features for the classification of dermoscopy images. The texture features consist of a variation of local binary pattern (LBP) in which the strength of the LBPs is used to extract scale adaptive patterns at each pixel, followed by the construction of a histogram. For color feature extraction, we used standard HSV histograms. The extracted features are concatenated to form a feature vector for an image, followed by classification using support vector machines. Experiments show that the proposed feature set exhibits good classification performance comparing favorably to other state-of-the-art alternatives. © 2014 IEEE.